Species-Level Classification and Mapping of a Mangrove Forest Using Random Forest - Utilisation of AVIRIS-NG and Sentinel Data

Although studies on species-level classification and mapping using multisource data and machine learning approaches are plenty, the use of data with ideal placement of central wavelength and bandwidth at appropriate spatial resolution, for the classification of mangrove species is underreported. The species composition of a mangrove forest has been estimated utilising the red-edge spectral bands and chlorophyll absorption information from AVIRIS-NG and Sentinel-2 data. In this study, three dominant species, Heritiera fomes, Excoecaria agallocha and Avicennia officinalis, have been classified using the random forest (RF) model for a mangrove forest in Bhitarkanika Wildlife Sanctuary, India. Various combinations of reflectance/backscatter bands and vegetation indices derived from Sentinel-2, AVIRIS-NG, and Sentinel-1 were used for species-level discrimination and mapping. The RF model showed maximum accuracy using Sentinel-2, followed by the AVIRIS-NG, in discriminating three dominant species and two mixed compositions. This study indicates the potential of Sentinel-2 data for discriminating various mangrove species owing to the appropriate placement of central wavelength and bandwidth in Sentinel-2 at ≥10 m spatial resolution. The variable importance plots proved that species-level classification could be attempted using red edge and chlorophyll absorption information. This study has wider applicability in other mangrove forests around the world.

[1]  Run Wang,et al.  Evaluating the Performance of Sentinel-2, Landsat 8 and Pléiades-1 in Mapping Mangrove Extent and Species , 2018, Remote. Sens..

[2]  Akash Anand,et al.  Spatial distribution of mangrove forest species and biomass assessment using field inventory and earth observation hyperspectral data , 2019, Biodiversity and Conservation.

[3]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[4]  Dirk Pflugmacher,et al.  Forest Stand Species Mapping Using the Sentinel-2 Time Series , 2019, Remote. Sens..

[5]  Koreen Millard,et al.  On the Importance of Training Data Sample Selection in Random Forest Image Classification: A Case Study in Peatland Ecosystem Mapping , 2015, Remote. Sens..

[6]  P. Kempeneers,et al.  Chlorophyll content estimation in an open-canopy conifer forest with Sentinel-2A and hyperspectral imagery in the context of forest decline , 2019, Remote sensing of environment.

[7]  Hui Lin,et al.  Textural-Spectral Feature-Based Species Classification of Mangroves in Mai Po Nature Reserve from Worldview-3 Imagery , 2015, Remote. Sens..

[8]  Giles M. Foody,et al.  Harshness in image classification accuracy assessment , 2008 .

[9]  M. Cho,et al.  Classification of savanna tree species, in the Greater Kruger National Park region, by integrating hyperspectral and LiDAR data in a Random Forest data mining environment , 2012 .

[10]  Testing the efficacy of hyperspectral (AVIRIS-NG), multispectral (Sentinel-2) and radar (Sentinel-1) remote sensing images to detect native and invasive non-native trees , 2021 .

[11]  Arundhati Misra,et al.  Mangrove Species Discrimination and Health Assessment using AVIRIS-NG Hyperspectral Data , 2019, Current Science.

[12]  Lin Liu,et al.  Object-Based Mangrove Species Classification Using Unmanned Aerial Vehicle Hyperspectral Images and Digital Surface Models , 2018, Remote. Sens..

[13]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[14]  Hui Lin,et al.  Potential of Combining Optical and Dual Polarimetric SAR Data for Improving Mangrove Species Discrimination Using Rotation Forest , 2018, Remote. Sens..

[15]  Robert O. Green,et al.  An Overview of AVIRIS-NG Airborne Hyperspectral Science Campaign Over India , 2019, Current Science.

[16]  Meiling Liu,et al.  Neural-network model for estimating leaf chlorophyll concentration in rice under stress from heavy metals using four spectral indices , 2010 .

[17]  R. Lucas,et al.  Aberystwyth University Distribution and Drivers of Global Mangrove Forest Change, 1996-2010 , 2017 .

[18]  G. Rondeaux,et al.  Optimization of soil-adjusted vegetation indices , 1996 .

[19]  Sudip Manna,et al.  Mapping distribution of Sundarban mangroves using Sentinel-2 data and new spectral metric for detecting their health condition , 2020, Geocarto International.

[20]  John M. Kovacs,et al.  Examining the Influence of Seasonality, Condition, and Species Composition on Mangrove Leaf Pigment Contents and Laboratory Based Spectroscopy Data , 2016, Remote. Sens..

[21]  Benjamin W. Heumann.  An Object-Based Classification of Mangroves Using a Hybrid Decision Tree - Support Vector Machine Approach , 2011, Remote. Sens..

[22]  Subash Dahal,et al.  A Multi-Sensor Approach for Assessing Mangrove Biophysical Characteristics in Coastal Odisha, India , 2017 .

[23]  Yuri A. Gritz,et al.  Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves. , 2003, Journal of plant physiology.

[24]  Karen E. Joyce,et al.  Mangrove Species Identification: Comparing WorldView-2 with Aerial Photographs , 2014, Remote. Sens..

[25]  M. Ashton,et al.  Accuracy assessments of hyperspectral waveband performance for vegetation analysis applications , 2004 .

[26]  P. Dennison,et al.  Retrieval of Atmospheric Parameters and Data-Processing Algorithms forAVIRIS-NG Indian Campaign Data , 2019, Current Science.

[27]  Gary R. Watmough,et al.  Evaluating the capabilities of Sentinel-2 for quantitative estimation of biophysical variables in vegetation , 2013 .

[28]  Ramanathan Sugumaran,et al.  Classification of Iowa wetlands using an airborne hyperspectral image: a comparison of the spectral angle mapper classifier and an object-oriented approach , 2005 .

[29]  Steffen Gebhardt,et al.  Remote Sensing of Mangrove Ecosystems: A Review , 2011, Remote. Sens..

[30]  Naoto Yokoya,et al.  Probabilistic Mangrove Species Mapping with Multiple-Source Remote-Sensing Datasets Using Label Distribution Learning in Xuan Thuy National Park, Vietnam , 2020, Remote. Sens..

[31]  Yali Liu,et al.  Separating Mangrove Species and Conditions Using Laboratory Hyperspectral Data: A Case Study of a Degraded Mangrove Forest of the Mexican Pacific , 2014, Remote. Sens..

[32]  Dieu Tien Bui,et al.  Optimized rule-based logistic model tree algorithm for mapping mangrove species using ALOS PALSAR imagery and GIS in the tropical region , 2018, Environmental Earth Sciences.

[33]  S. P. S. Kushwaha,et al.  Forest Vegetation Characterization and Mapping Using IRS-1C Satellite Images in Eastern Himalayan Region , 2001 .

[34]  D. Horler,et al.  The red edge of plant leaf reflectance , 1983 .

[35]  Craig S. T. Daughtry,et al.  A visible band index for remote sensing leaf chlorophyll content at the canopy scale , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[36]  Uwe Stilla,et al.  Machine Learning Comparison between WorldView-2 and QuickBird-2-Simulated Imagery Regarding Object-Based Urban Land Cover Classification , 2011, Remote. Sens..

[37]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[38]  Hongxing Liu,et al.  Retrieval of Mangrove Aboveground Biomass at the Individual Species Level with WorldView-2 Images , 2015, Remote. Sens..

[39]  Wenjiang Huang,et al.  Remote estimation of gross primary production in wheat using chlorophyll-related vegetation indices , 2009 .

[40]  M. D. Behera,et al.  Annual and seasonal variations in gross primary productivity across the agro-climatic regions in India , 2019, Environmental Monitoring and Assessment.

[41]  Tung Fung,et al.  Combining EO-1 Hyperion and Envisat ASAR data for mangrove species classification in Mai Po Ramsar Site, Hong Kong , 2014 .

[42]  John A. Silander,et al.  Delineating forest canopy species in the northeastern united states using multi-temporal TM imagery , 1998 .

[43]  Sourav Samanta,et al.  An index for discrimination of mangroves from non-mangroves using LANDSAT 8 OLI imagery , 2018, MethodsX.

[44]  A. C. Ellis,et al.  Remote sensing techniques for mangrove mapping , 1998 .

[45]  Sushma Panigrahy,et al.  Classification of floristic composition of mangrove forests using hyperspectral data: case study of Bhitarkanika National Park, India , 2013, Journal of Coastal Conservation.

[46]  Kenji Omasa,et al.  Comparing vegetation indices for remote chlorophyll measurement of white poplar and Chinese elm leaves with different adaxial and abaxial surfaces , 2015, Journal of experimental botany.

[47]  O. Mutanga,et al.  Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review , 2010, Wetlands Ecology and Management.

[48]  A. Kulkarni,et al.  Random Forest Algorithm for Land Cover Classification , 2016 .

[49]  Mukunda Dev Behera,et al.  Aboveground biomass estimates of tropical mangrove forest using Sentinel-1 SAR coherence data - The superiority of deep learning over a semi-empirical model , 2021, Comput. Geosci..

[50]  A. Blanco,et al.  Development and application of a new mangrove vegetation index (MVI) for rapid and accurate mangrove mapping , 2020, ISPRS Journal of Photogrammetry and Remote Sensing.

[51]  Mukunda Dev Behera,et al.  Canopy Height Estimation Using Sentinel Series Images through Machine Learning Models in a Mangrove Forest , 2020, Remote. Sens..

[52]  J. Dash,et al.  The MERIS terrestrial chlorophyll index , 2004 .

[53]  Hongsheng Zhang,et al.  Exploring the optimal integration levels between SAR and optical data for better urban land cover mapping in the Pearl River Delta , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[54]  Fatwa Ramdani,et al.  Principal polar spectral indices for mapping mangroves forest in South East Asia: study case Indonesia , 2019, Int. J. Digit. Earth.

[55]  Shoufan Fang,et al.  The Impact of Misclassification in Land Use Maps in the Prediction of Landscape Dynamics , 2006, Landscape Ecology.